jmaczan/curiosity
Low-level deep learning concepts from scratch
This project helps deep learning practitioners understand the foundational concepts behind neural networks by implementing them from scratch. You provide a C file containing tensor or multi-layer perceptron (MLP) definitions and it will train or run your model. It's for data scientists, machine learning engineers, or students who want to delve into the mathematical and computational underpinnings of deep learning without relying on high-level frameworks.
No commits in the last 6 months.
Use this if you want to learn how fundamental deep learning components like tensors and multi-layer perceptrons are built and operate at a low level.
Not ideal if you need to quickly build or deploy complex deep learning models for real-world applications using established libraries.
Stars
12
Forks
1
Language
C
License
—
Category
Last pushed
Jun 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jmaczan/curiosity"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Dobiasd/frugally-deep
A lightweight header-only library for using Keras (TensorFlow) models in C++.
flashlight/flashlight
A C++ standalone library for machine learning
wichtounet/dll
Fast Deep Learning Library (DLL) for C++ (ANNs, CNNs, RBMs, DBNs...)
NVlabs/tiny-cuda-nn
Lightning fast C++/CUDA neural network framework
KasperskyLab/knp
Kaspersky Neuromorphic Platform